Skip to content

Commit caf6e0d

Browse files
authored
test(runner-shared): search artifacts of up to 100M events in the module event bench
With frames decoded in parallel, CI-sized artifacts are fast enough to benchmark again: add the 10M and 100M event sizes the streamed decoder was too slow for. The 100M artifact with stacks is about 5 GB on disk and is mapped, not held in memory.
1 parent c869009 commit caf6e0d

1 file changed

Lines changed: 4 additions & 4 deletions

File tree

‎crates/runner-shared/benches/memtrack_reader.rs‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -16,10 +16,10 @@ fn main() {
1616
divan::main();
1717
}
1818

19-
/// Artifact sizes in events: as many as `encode_events_realistic` encodes, 16
20-
/// encoder frames. CI-sized artifacts take minutes per case with the streamed
21-
/// decoder under the simulation instrument.
22-
const SIZES: &[usize] = &[16 * 64 * 1024];
19+
/// Artifact sizes in events: from as many as `encode_events_realistic`
20+
/// encodes up to a CI-sized artifact, with enough frames to show how the
21+
/// parallel frame scan scales.
22+
const SIZES: &[usize] = &[16 * 64 * 1024, 10_000_000, 100_000_000];
2323

2424
#[derive(Clone, Copy)]
2525
enum Payload {

0 commit comments

Comments
 (0)